V01D by A-to-Mind
Ask Void anything: answers with sources, plus code review, moon phases and meteor showers.
我該用這個嗎
品質與安全性
發現項目（2）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 review_code_closer 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"void": {
"url": "https://a-to-mind.com/api/mcp"
}
}
}遠端端點
https://a-to-mind.com/api/mcpstreamable-http它能做什麼
工具清單
工具（5）
🟢ask_void(ask)
Ask Void a question in plain words and get its answer: a short, direct answer from Void's answer engine (a-to-mind.com), citing the Wikipedia pages it drew on when they match. Ask about Void itself ("what are you building?") and it answers from its own live facts. Up to 12 model answers a minute per caller; a repeated question may come from the 7-day cache.
輸入結構描述
{
"type": "object",
"properties": {
"ask": {
"type": "string",
"description": "The question, in plain words (3 to 600 characters)."
}
},
"required": [
"ask"
]
}🟢review_code(code, diff, lang)
Void's instant code review: pattern checks for bugs, risks and style in pasted code or a diff's added lines, in many languages. The same checks a-to-mind.com runs when someone asks Void to review code. No model; the closer read is not included. Its structured result says basis 'patterns' and confidence 'low'.
輸入結構描述
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The code to review (up to 60,000 characters)."
},
"diff": {
"type": "string",
"description": "A unified diff instead of code: only the added lines are reviewed, with their line numbers in the new file."
},
"lang": {
"type": "string",
"description": "The language, if known (javascript, python, go, rust, sql, ...)."
}
}
}🟢review_code_closer(code, diff, lang)
Void's code review with the closer read: the instant checks, then an AI reviewer that confirms real findings, drops wrong ones and adds what the patterns missed, each quoting its line. The closer read needs a key in the MCP request's Authorization header (Bearer: a Void Pro review key vr1.… or a Void Code Review Pro license key; https://a-to-mind.com/code-review/#pro). Without one you get the instant checks and how to get it. The structured result says what it rests on: basis 'closer_read' (confidence 'reviewed') only when the closer read came back, else 'patterns' (confidence 'low').
輸入結構描述
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The code to review (up to 60,000 characters)."
},
"diff": {
"type": "string",
"description": "A unified diff instead of code: the added lines are reviewed."
},
"lang": {
"type": "string",
"description": "The language, if known."
}
}
}🟢moon_phase(date)
The moon's illuminated fraction, whether it is waxing or waning, and the phase's name for a moment, from Meeus' formulas (Astronomical Algorithms, ch. 47-48).
輸入結構描述
{
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "An ISO date or date-time (UTC). Leave it out for now."
}
}
}🟢meteor_showers(date)
The meteor showers active on a date (strongest first, with days to each peak and the peak rate) and the next peak on or after it, from the IMO calendar of the major showers.
輸入結構描述
{
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "An ISO date or date-time (UTC). Leave it out for now."
}
}
}社群
證據